> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Video Generation Overview

> Call all video generation models through the unified /v1/tasks endpoint, async submit, async retrieve

QWave API supports many video generation models, **all called through the unified async task endpoint** `/v1/tasks`. Video generation typically takes from 10 seconds up to several minutes; after submission you receive a `task_id`, and you fetch the result via polling or a webhook callback.

## Request Endpoint

```
POST https://www.qingbo.dev/v1/tasks
```

For the full async flow see [Task System](/en/docs/task-system) — Submit → Status → Result + optional webhook.

## Supported Models

<CardGroup cols={2}>
  <Card title="Veo Series" href="/en/api-reference/video/veo">
    Google Veo 3.1 — official direct (Fast / Quality) + reverse-engineered (Lite / Quality)
  </Card>

  <Card title="Seedance Series" href="/en/api-reference/video/seedance">
    ByteDance Seedance — 1.0 Pro / 1.5 Pro / 2.0 (with Face / Fast variants)
  </Card>

  <Card title="Kling Series" href="/en/api-reference/video/kling">
    Kuaishou Kling — v2.6 / v3 / v3-Omni / Video O1
  </Card>

  <Card title="Hailuo Series" href="/en/api-reference/video/hailuo">
    MiniMax Hailuo — 2.3 / 2.3 Fast, 15 camera-movement directives
  </Card>

  <Card title="Vidu Series" href="/en/api-reference/video/vidu">
    Shengshu Vidu Q3 — Pro / Mix / Q3 / Turbo
  </Card>

  <Card title="Wan Series" href="/en/api-reference/video/wan">
    Alibaba Tongyi Wanxiang — 2.7 VideoEdit (video editing / style transfer)
  </Card>

  <Card title="Skyreels" href="/en/api-reference/video/skyreels">
    Kunlun Wanwei SkyReels V4 — Fast / Standard, multimodal reference
  </Card>

  <Card title="HappyHorse" href="/en/api-reference/video/happyhorse">
    Alibaba Cloud Bailian HappyHorse — single model auto-routes T2V/I2V/R2V/EDIT
  </Card>

  <Card title="Grok Imagine Video" href="/en/api-reference/video/grok-imagine-video">
    xAI Grok Imagine 1.0 Video — 6-30 seconds, 5 aspect ratios
  </Card>
</CardGroup>

## Common Parameters (shared across the series)

> Each model's actual supported range differs — **see the individual vendor docs**.

<ParamField body="model" type="string" required>
  Model ID (group\_name); pick from the vendor docs above
</ParamField>

<ParamField body="action" type="string" default="generate">
  Operation type; valid values depend on the model. Common values:

  * `generate` — text-to-video (T2V)
  * `image2video` — image-to-video (I2V)
  * `first_last_frame` — first/last frame
  * `reference` / `reference_video` — reference-to-video (R2V)
  * `edit` / `video_edit` / `style_transfer` — video editing
  * `video_continuation` / `extend` — video continuation
</ParamField>

<ParamField body="prompt" type="string">
  Video description text. Required for T2V; optional as guidance for other modes
</ParamField>

<ParamField body="duration" type="integer">
  Video duration in seconds; range depends on the model
</ParamField>

<ParamField body="aspect_ratio" type="string">
  Frame aspect ratio, e.g. `16:9` / `9:16` / `1:1`
</ParamField>

<ParamField body="resolution" type="string">
  Output resolution, e.g. `720p` / `1080p` / `4K`
</ParamField>

<ParamField body="image_urls" type="string[]">
  Array of reference image URLs (used for I2V / R2V)
</ParamField>

<ParamField body="first_frame_image" type="string">
  First-frame image URL (used for first/last-frame mode)
</ParamField>

<ParamField body="last_frame_image" type="string">
  Last-frame image URL; must be paired with `first_frame_image`
</ParamField>

<ParamField body="video_urls" type="string[]">
  Array of reference video URLs — **a single element is sufficient** (used for video continuation / R2V video reference / video editing)
</ParamField>

<ParamField body="audio_urls" type="string[]">
  Array of reference audio URLs — **a single element is sufficient** (used for driving audio / custom voiceover)
</ParamField>

<ParamField body="callback_url" type="string">
  Webhook callback URL, invoked when the task reaches a terminal state. See [Task System](/en/docs/task-system#webhook)
</ParamField>

## Submit Response Example

```json theme={"system"}
{
  "task_id": "task-wave1775285160b950328499",
  "model": "veo3.1-quality-official",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}
```

After receiving `task_id`, poll [`GET /v1/tasks/{task_id}`](/en/api-reference/task/status) until `status = completed`, then read the video URL.

## Mode Quick Reference

| Mode                            | Trigger Fields                                                     | Typical Vendors                                                 |
| ------------------------------- | ------------------------------------------------------------------ | --------------------------------------------------------------- |
| **Text-to-video (T2V)**         | `prompt` only                                                      | All vendors that support the generate action                    |
| **Image-to-video (I2V)**        | `+ first_frame_image` or `image_urls` (single image)               | Seedance / Kling / Hailuo / Vidu Pro / Wan / Veo / Sky / Grok   |
| **First/last frame**            | `first_frame_image + last_frame_image`                             | Seedance Pro Quality / 1.5 / 2.0 / Kling / Veo / Vidu Pro / Sky |
| **Reference-to-video (R2V)**    | `image_urls` (multiple, 1-9 images)                                | Seedance / Kling Omni / Vidu / Sky / HappyHorse                 |
| **Video reference (R2V video)** | `+ video_urls` (reference video)                                   | Seedance 2.0 / Kling Omni / Sky / Wan                           |
| **Video continuation**          | `video_urls` (single clip)                                         | Wan (other tiers not yet available) / Sky                       |
| **Video editing (EDIT)**        | `video_urls + prompt` (optionally `image_urls` as style reference) | Wan VideoEdit / HappyHorse / Sky                                |
| **Audio reference**             | `+ audio_urls`                                                     | HappyHorse / Wan / Sky / Seedance 2.0                           |

<Note>
  Not every model supports every mode — check each vendor's doc for the actual supported `action` list and field range. The backend validates whether request fields fall within the vendor's declared capabilities and returns an error if they do not.
</Note>

## Field Naming Conventions

* **Media references are always plural** — always `image_urls` / `video_urls` / `audio_urls`; even a single video uses a one-element array `["one.mp4"]`
* **Frame ratio is unified as** `aspect_ratio` — vendor-internal `size` / `ratio` etc. are implementation details and not exposed
* **Resolution is unified as** `resolution` — vendor-internal `mode` / `quality` etc. are implementation details
* **First/last-frame fields carry the `_image` suffix** — `first_frame_image` / `last_frame_image` (emphasizing the image resource)

## Related Docs

* [Task System Reference](/en/docs/task-system) — task state machine / polling cadence / webhook
* [Request and Response Format](/en/docs/request-response) — common error codes / headers / rate limits
* [Authentication](/en/docs/authentication) — API key application and usage
* [Model List](/en/docs/models) — full model list query endpoint